ST-GDance: Long-Term and Collision-Free Group Choreography from Music


Jing Xu (Monash University), Weiqiang Wang (Monash University), Cunjian Chen (Monash University), Jun Liu (Lancaster University), Qiuhong Ke (Monash University)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly applicable in film, gaming, and animation production. However, as the number of dancers and the sequence length increase, the task becomes computationally expensive and the risk of motion collisions rises. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often fail to capture such complexity, resulting in poor scalability and frequent multi-dancer collisions. To address these challenges, we propose ST-GDance, a novel framework that decouples spatial and temporal dependencies to optimize long-term and collision-free group choreography. We employ lightweight graph convolutions for distance-aware spatial modeling and accelerated sparse attention for efficient temporal modeling. This design significantly reduces computational costs while ensuring smooth and collision-free interactions. Experiments on the AIOZ-GDance dataset demonstrate that ST-GDance outperforms state-of-the-art baselines, particularly in generating long and coherent group dance sequences. Project page: https://yilliajing.github.io/ST-GDance-Website/.

Citation

@inproceedings{Xu_2025_BMVC,
author    = {Jing Xu and Weiqiang Wang and Cunjian Chen and Jun Liu and Qiuhong Ke},
title     = {ST-GDance: Long-Term and Collision-Free Group Choreography from Music},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_66/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection